阅读说明：本技术 基于神经网络的位置融合方法及系统、车载终端 (Position fusion method and system based on neural network and vehicle-mounted terminal ) 是由 穆允林 李欢 于 2018-07-19 设计创作，主要内容包括：本发明提供一种基于神经网络的位置融合方法及系统、车载终端,包括以下步骤：获取设置在车辆上的陀螺仪采集的陀螺仪数据；将所述陀螺仪数据、与所述陀螺仪数据对应的方向盘数据和车速输入神经网络,以对车辆各种行驶状态进行学习；根据所述神经网络的学习结果进行车辆位置融合计算。本发明的基于神经网络的位置融合方法及系统、车载终端基于神经网络对不同驾驶模式及状态下的位置误差进行学习,从而提高了方向盘辅助定位的精确度。(The invention provides position fusion methods and systems based on a neural network and a vehicle-mounted terminal, which comprise the following steps of obtaining gyroscope data collected by a gyroscope arranged on a vehicle, inputting the gyroscope data, steering wheel data corresponding to the gyroscope data and vehicle speed into the neural network to learn various driving states of the vehicle, and performing vehicle position fusion calculation according to the learning result of the neural network.)

1, A neural network-based location fusion method, which is characterized by comprising the following steps:

acquiring gyroscope data acquired by a gyroscope arranged on a vehicle;

inputting the gyroscope data, steering wheel data corresponding to the gyroscope data and vehicle speed into a neural network so as to learn various driving states of the vehicle;

and carrying out vehicle position fusion calculation according to the learning result of the neural network.

2. The neural network-based location fusion method of claim 1, wherein: acquiring gyroscope data collected by a gyroscope disposed on a vehicle includes:

judging the reliability of the acquired gyroscope data;

and screening the gyroscope data with the credibility greater than a preset threshold value.

3. The neural network-based location fusion method of claim 1, wherein: the steering wheel data includes steering wheel zero drift and angle coefficients of range.

4. The neural network-based location fusion method of claim 1, wherein: the vehicle running state comprises acceleration, deceleration and uniform speed.

5, kinds of position fusion system based on neural network, which is characterized in that the system comprises an acquisition module, a learning module and a calculation module;

the acquisition module is used for acquiring gyroscope data acquired by a gyroscope arranged on a vehicle;

the learning module is used for inputting the gyroscope data, the steering wheel data corresponding to the gyroscope data and the vehicle speed into a neural network so as to learn various driving states of the vehicle;

and the calculation module is used for carrying out vehicle position fusion calculation according to the learning result of the neural network.

6. The neural network-based location fusion system of claim 5, wherein: the acquisition module acquires gyroscope data acquired by a gyroscope arranged on a vehicle and executes the following operations:

judging the reliability of the acquired gyroscope data;

and screening the gyroscope data with the credibility greater than a preset threshold value.

7. The neural network-based location fusion system of claim 5, wherein: the steering wheel data includes steering wheel zero drift and angle coefficients of range.

8. The neural network-based location fusion system of claim 5, wherein: the vehicle running state comprises acceleration, deceleration and uniform speed.

9, kinds of vehicle mounted terminals, characterized by comprising a processor and a memory;

the memory is used for storing a computer program;

the processor is configured to execute the computer program stored in the memory to cause the vehicle-mounted terminal to execute the neural network-based location fusion method of any of claims 1-4.

The neural network-based location fusion system of claim 10, , comprising the vehicle-mounted terminal, the gyroscope and the steering wheel data acquisition module of claim 9;

the gyroscope is used for acquiring gyroscope data and sending the gyroscope data to the vehicle-mounted terminal;

the steering wheel data acquisition module is used for acquiring steering wheel data and sending the steering wheel data to the vehicle-mounted terminal.

Technical Field

The invention relates to the technical field of steering wheel auxiliary positioning, in particular to position fusion methods and systems based on a neural network and a vehicle-mounted terminal.

Background

The steering wheel on the vehicle is used for converting the force applied to the edge of the steering wheel by the driver into torque and transmitting the torque to the steering shaft, so that the running state of the vehicle is controlled.

Disclosure of Invention

In view of the above-mentioned shortcomings of the prior art, the present invention aims to provide location fusion methods and systems based on neural networks, and vehicle-mounted terminals, which learn location errors in different driving modes and states based on neural networks, thereby improving the accuracy of steering wheel assisted positioning.

In order to achieve the above objects and other related objects, the present invention provides a neural network-based location fusion method, comprising the steps of acquiring gyroscope data collected by a gyroscope provided on a vehicle, inputting the gyroscope data, steering wheel data corresponding to the gyroscope data, and vehicle speed into a neural network to learn various driving states of the vehicle, and performing a location fusion calculation of the vehicle based on the learning results of the neural network.

In an embodiment of the present invention, acquiring gyroscope data collected by a gyroscope disposed on a vehicle includes:

judging the reliability of the acquired gyroscope data;

and screening the gyroscope data with the credibility greater than a preset threshold value.

In the embodiment of the present invention, the steering wheel data includes steering wheel zero drift and angle coefficients of range.

In the embodiment of the present invention, the driving status of the vehicle includes acceleration, deceleration, and uniform speed.

Correspondingly, the invention provides kinds of position fusion systems based on neural network, including obtaining module, learning module and calculating module;

the acquisition module is used for acquiring gyroscope data acquired by a gyroscope arranged on a vehicle;

the learning module is used for inputting the gyroscope data, the steering wheel data corresponding to the gyroscope data and the vehicle speed into a neural network so as to learn various driving states of the vehicle;

and the calculation module is used for carrying out vehicle position fusion calculation according to the learning result of the neural network.

In an embodiment of the present invention, the obtaining module obtains gyroscope data collected by a gyroscope disposed on a vehicle to perform the following operations:

judging the reliability of the acquired gyroscope data;

and screening the gyroscope data with the credibility greater than a preset threshold value.

In the embodiment of the present invention, the steering wheel data includes steering wheel zero drift and angle coefficients of range.

In the embodiment of the present invention, the driving status of the vehicle includes acceleration, deceleration, and uniform speed.

The invention provides vehicle-mounted terminals, which comprise a processor and a memory;

the memory is used for storing a computer program;

the processor is used for executing the computer program stored in the memory so as to enable the vehicle-mounted terminal to execute the neural network-based position fusion method.

Finally, the invention provides location fusion systems based on a neural network, which comprise the vehicle-mounted terminal, a gyroscope and a steering wheel data acquisition module;

the gyroscope is used for acquiring gyroscope data and sending the gyroscope data to the vehicle-mounted terminal;

the steering wheel data acquisition module is used for acquiring steering wheel data and sending the steering wheel data to the vehicle-mounted terminal.

As described above, the neural network-based location fusion method and system and the vehicle-mounted terminal of the present invention have the following advantages:

(1) the position errors in different driving modes and states are learned based on the neural network, so that the auxiliary positioning accuracy of the steering wheel is improved;

(2) the fault-tolerant capability of auxiliary positioning of the steering wheel is improved;

(3) the dependence degree on other modules on the vehicle is reduced, and the requirement on data synchronization is reduced;

(4) the manual operation of a user is not needed, and the user experience is greatly improved.

Drawings

FIG. 1 is a flow chart of a neural network-based location fusion method of the present invention in an embodiment ;

FIG. 2 is a block diagram illustrating an embodiment of a neural network based location fusion system according to the present invention;

FIG. 3 is a block diagram of an embodiment of the vehicle terminal according to the invention;

FIG. 4 is a schematic structural diagram illustrating another embodiment of the neural network-based location fusion system of the present invention.

Description of the element reference numerals

21 acquisition module

22 learning module

23 calculation module

31 processor

32 memory

41 vehicle-mounted terminal

42 gyroscope

43 steering wheel data acquisition module

Detailed Description

The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.

It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of each component in actual implementation can be random changes, and the layout of the components may be more complicated.

The position fusion method and system based on the neural network, and the vehicle-mounted terminal learn the position errors in different driving modes and states based on the neural network, and reduce the angle and position weights calculated by dead reckoning, thereby quickly correcting the errors and improving the accuracy of steering wheel auxiliary positioning.

As shown in fig. 1, in , the neural network-based location fusion method of the present invention includes the following steps:

and step S1, acquiring gyroscope data collected by a gyroscope arranged on the vehicle.

In particular, in the case where a gyroscope is disposed on a vehicle, acquiring gyroscope data collected by the gyroscope in an embodiment of the present invention, acquiring gyroscope data collected by a gyroscope disposed on the vehicle includes:

11) and judging the reliability of the acquired gyroscope data.

Specifically, the reliability of the gyro data is judged for the running state of the vehicle. The reliability of the gyroscope data matched with the vehicle running state is relatively high; the reliability of the gyro data that does not match the running state of the vehicle is relatively low.

12) And screening the gyroscope data with the credibility greater than a preset threshold value.

Specifically, only the gyroscope data with the reliability greater than the preset threshold is selected as the training data for subsequent use.

And step S2, inputting the gyroscope data, the steering wheel data corresponding to the gyroscope data and the vehicle speed into a neural network so as to learn various driving states of the vehicle.

Specifically, the steering wheel data and the vehicle speed at the time corresponding to the gyro data are input to the neural network together with the gyro data , and various driving states of the vehicle are learned.

In the embodiment of the present invention, the steering wheel data includes steering wheel zero drift and angle coefficients of range.

Neural Networks (NNs) are complex network systems formed by a large number of simple processing units (called neurons) widely interconnected, reflecting many of the basic features of human brain function, which are highly complex nonlinear dynamical learning systems Neural Networks have massively parallel, distributed storage and processing, self-organizing, adaptive and self-learning capabilities, and are particularly well suited to handle information processing problems that require simultaneous consideration of many factors and conditions, both fuzzy and artificial, and are related to neuroscience, mathematical science, cognitive science, computer science, artificial intelligence, information science, control theory, robotics, microelectronics, psychology, optical computing, molecular biology, etc., an emerging edge cross discipline Neural network model is described based on mathematical models of neurons.

In the embodiment of the present invention, the driving status of the vehicle includes acceleration, deceleration, and uniform speed.

And step S3, carrying out vehicle position fusion calculation according to the learning result of the neural network.

Specifically, the learning result of the neural network is applied to vehicle position fusion calculation, so that under the condition that a gyroscope is not arranged, the weight of the dead reckoning angle and position is reduced, errors are quickly corrected, and the fault tolerance of steering wheel auxiliary positioning is improved.

It should be noted that the position fusion calculation refers to combining positioning and dead reckoning of a Global Navigation Satellite System (GNSS), and under the cooperation of a calculation model (such as a position estimation model, an error influence, an error correction, and the like) and a multi-sensor fusion algorithm (such as an extended kalman filter algorithm), fusion positions with higher precision and higher frequency are generated according to respective error ranges of positioning of the two, so that the position fusion calculation has self-adaptive correction capability while optimizing the position.

As shown in fig. 2, in , the neural network based location fusion system of the present invention includes an obtaining module 21, a learning module 22, and a calculating module 23.

The obtaining module 21 is configured to obtain gyroscope data collected by a gyroscope disposed on the vehicle.

In the embodiment of the present invention, the obtaining module 21 obtains the gyroscope data collected by the gyroscope disposed on the vehicle by performing the following steps:

11) and judging the reliability of the acquired gyroscope data.

Specifically, the reliability of the gyro data is judged for the running state of the vehicle. The reliability of the gyroscope data matched with the vehicle running state is relatively high; the reliability of the gyro data that does not match the running state of the vehicle is relatively low.

12) And screening the gyroscope data with the credibility greater than a preset threshold value.

Specifically, only the gyroscope data with the reliability greater than the preset threshold is selected as the training data for subsequent use.

The learning module 22 is connected to the obtaining module 21, and is configured to input the gyroscope data, steering wheel data corresponding to the gyroscope data, and a vehicle speed into a neural network, so as to learn various driving states of the vehicle.

Specifically, the steering wheel data and the vehicle speed at the time corresponding to the gyro data are input to the neural network together with the gyro data , and various driving states of the vehicle are learned.

In the embodiment of the present invention, the steering wheel data includes steering wheel zero drift and angle coefficients of range.

Neural Networks (NNs) are complex network systems formed by a large number of simple processing units (called neurons) widely interconnected, reflecting many of the basic features of human brain function, which are highly complex nonlinear dynamical learning systems Neural Networks have massively parallel, distributed storage and processing, self-organizing, adaptive and self-learning capabilities, and are particularly well suited to handle information processing problems that require simultaneous consideration of many factors and conditions, both fuzzy and artificial, and are related to neuroscience, mathematical science, cognitive science, computer science, artificial intelligence, information science, control theory, robotics, microelectronics, psychology, optical computing, molecular biology, etc., an emerging edge cross discipline Neural network model is described based on mathematical models of neurons.

In the embodiment of the present invention, the driving status of the vehicle includes acceleration, deceleration, and uniform speed.

The calculation module 23 is connected to the learning module 22, and is configured to perform vehicle position fusion calculation according to the learning result of the neural network.

Specifically, the learning result of the neural network is applied to vehicle position fusion calculation, so that under the condition that a gyroscope is not arranged, the weight of the dead reckoning angle and position is reduced, errors are quickly corrected, and the fault tolerance of steering wheel auxiliary positioning is improved.

It should be noted that the position fusion calculation refers to combining positioning and dead reckoning of a Global Navigation Satellite System (GNSS), and under the cooperation of a calculation model (such as a position estimation model, an error influence, an error correction, and the like) and a multi-sensor fusion algorithm (such as an extended kalman filter algorithm), fusion positions with higher precision and higher frequency are generated according to respective error ranges of positioning of the two, so that the position fusion calculation has self-adaptive correction capability while optimizing the position.

It should be noted that the division of each module of the above system is merely a division of logic functions, and all or part of the modules may be integrated into physical entities or physically separated when actually implemented, and all the modules may be implemented in the form of software called by a processing element, or all the modules may be implemented in the form of hardware, or part of the modules may be implemented in the form of software called by a processing element, and part of the modules may be implemented in the form of hardware.

For example, these modules may be or more integrated circuits configured to implement the above method, such as or more specific integrated circuits (ASIC), or or more microprocessors (DSP), or or more Field Programmable Gate Arrays (FPGA), etc. further, when the above modules are implemented in the form of a processing element scheduler code, the processing element may be a general purpose processor, such as a Central Processing Unit (CPU) or other processor that can call up the program code.

As shown in fig. 3, in the embodiment, the vehicle-mounted terminal of the invention includes a processor 31 and a memory 32.

The memory 32 is used for storing computer programs.

The memory 32 includes: various media that can store program codes, such as ROM, RAM, magnetic disk, U-disk, memory card, or optical disk.

The processor 31 is connected to the memory 32 and configured to execute the computer program stored in the memory 32, so that the vehicle-mounted terminal executes the neural network-based location fusion method described above.

Preferably, the processor 31 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc., a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field programmable array (FPGA), or other programmable logic device, discrete , or a transistor logic device, discrete hardware components.

As shown in fig. 4, in , the neural network-based location fusion system of the present invention includes the above-mentioned vehicle-mounted terminal 41, gyroscope 42, and steering wheel data collection module 43.

The gyroscope 42 is connected with the vehicle-mounted terminal 41 and used for acquiring gyroscope data and sending the gyroscope data to the vehicle-mounted terminal 41.

The steering wheel data acquisition module 43 is connected to the vehicle-mounted terminal 41, and is configured to acquire steering wheel data and send the steering wheel data to the vehicle-mounted terminal 41.

In summary, the position fusion method and system based on the neural network, and the vehicle-mounted terminal learn the position errors in different driving modes and states based on the neural network, so that the steering wheel auxiliary positioning accuracy is improved; the fault-tolerant capability of auxiliary positioning of the steering wheel is improved; the dependence degree on other modules on the vehicle is reduced, and the requirement on data synchronization is reduced; the manual operation of a user is not needed, and the user experience is greatly improved. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.

It will be appreciated by those skilled in the art that modifications and variations can be made to the disclosed embodiments without departing from the spirit and scope of the invention, and therefore, is equivalent to modifications and variations that would be apparent to those skilled in the art without departing from the spirit and scope of the invention as disclosed in the appended claims.